A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Universal Multi-Source Domain Adaptation
[article]
2020
arXiv
pre-print
Preserved Fulltext
Recent study reveals that knowledge can be transferred from one source domain to another unknown target domain, called Universal Domain Adaptation (UDA). ...
In this paper, we formally propose a more general domain adaptation setting, universal multi-source domain adaptation (UMDA), where the label sets of multiple source domains can be different and the label ...
, open set domain adaptation and universal domain adaptation. ...
arXiv:2011.02594v1
fatcat:5h53zhcwzjdvffivlkktpixrlm
Universal Source-Free Domain Adaptation
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
a domain-shift. ...
Existing domain adaptation (DA) approaches are not equipped for practical DA scenarios as a result of their reliance on the knowledge of source-target label-set relationship (e.g. ...
In summary, we propose a convenient DA framework, which is equipped to address Universal Source-Free Domain Adaptation. ...
arXiv:2004.04393v1
fatcat:frfnm6ybmngzfg5jr2aawr7xwm
Universal Source-Free Domain Adaptation
2020
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
domain-shift. ...
Existing domain adaptation (DA) approaches are not equipped for practical DA scenarios as a result of their reliance on the knowledge of source-target label-set relationship (e.g. ...
In summary, we propose a convenient DA framework, which is equipped to address Universal Source-Free Domain Adaptation. ...
doi:10.1109/cvpr42600.2020.00460
dblp:conf/cvpr/KunduVVB20
fatcat:szkbu7xtjzcw5aufkrp76x36ji
Universal Domain Adaptive Object Detector
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Universal domain adaptive object detection (UniDAOD)is more challenging than domain adaptive object detection (DAOD) since the label space of the source domain may not be the same as that of the target ...
To this end, we propose US-DAF, namely Universal Scale-Aware Domain Adaptive Faster RCNN with Multi-Label Learning, to reduce the negative transfer effect during training while maximizing transferability ...
(PADA) [1] , (4) Universal domain adaptation methods: Universal Adaptation Network (UAN) [34] , Calibrated Multiple Uncertainties (CMU) [7] . ...
arXiv:2207.01756v1
fatcat:6wuzufnrvnf2ph4cjl6klbuxau
Provably Uncertainty-Guided Universal Domain Adaptation
[article]
2023
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2023; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2023 pre-print arXiv:2209.09616v7 fatcat:2ci4ax6eane2xbuwm6zjw5j63iOther Versions
Universal domain adaptation (UniDA) aims to transfer the knowledge from a labeled source domain to an unlabeled target domain without any assumptions of the label sets, which requires distinguishing the ...
unknown samples from the known ones in the target domain. ...
[18] employed selfsupervised learning to separate the known and unknown samples and complete the domain alignment.
Universal Domain Adaptation UniDA, which is firstly introduced by You et al. ...
arXiv:2209.09616v8
fatcat:oudk435npbf33nbpbqzmyjpxuy
Sample Selection for Universal Domain Adaptation
2021
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
This paper studies the problem of unsupervised domain adaption in the universal scenario, in which only some of the classes are shared between the source and target domains. ...
The score is used to select samples in the target domain for which to apply specific losses during training; pseudo-labels for high scoring samples and confidence regularization for low scoring samples ...
Table 1 : 1 Domain adaptation methods. Uni=universal. ...
doi:10.1609/aaai.v35i10.17042
fatcat:jrc3qwyg7rc7zppsmayxivssdm
Universal Domain Adaptation in Ordinal Regression
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We address the problem of universal domain adaptation (UDA) in ordinal regression (OR), which attempts to solve classification problems in which labels are not independent, but follow a natural order. ...
Combined with adversarial domain discrimination, our model is able to address the closed set, partial and open set configurations. ...
UNIVERSAL DOMAIN ADAPTATION IN OR We address the problem of Universal Domain Adaptation in OR, where a source domain D s = {(x i s , y i s )} consisting of n s labeled samples and a target domain D t = ...
arXiv:2106.11576v2
fatcat:hj3xmrlmifcuhk2zrcb6wtrrue
Universal Domain Adaptation through Self Supervision
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We propose a more universally applicable domain adaptation framework that can handle arbitrary category shift, called Domain Adaptative Neighborhood Clustering via Entropy optimization (DANCE). ...
Unsupervised domain adaptation methods traditionally assume that all source categories are present in the target domain. ...
We use the following released codes for ETN [3] (https://github.com/thuml/ETN), UAN [44] (https://github.com/thuml/ Universal-Domain-Adaptation), and STA [24] (https://github.com/thuml/Separate_ to_Adapt ...
arXiv:2002.07953v3
fatcat:uhicmnwvkbeljb5pjrov45mohi
HyperDomainNet: Universal Domain Adaptation for Generative Adversarial Networks
[article]
2023
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2023; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Inspired by the reduction in the size of the optimizing parameter space we consider the problem of multi-domain adaptation of GANs, i.e. setting when the same model can adapt to several domains depending ...
We introduce a novel domain-modulation technique that allows to optimize only 6 thousand-dimensional vector instead of 30 million weights of StyleGAN2 to adapt to a target domain. ...
Designing the HyperDomainNet for Universal Domain Adaptation The proposed domain-modulation technique allows us to reduce the number of trainable parameters which motivates us to tackle the problem of ...
arXiv:2210.08884v4
fatcat:mf436ytg4jhcvgvwbn5txw7kx4
Universal Domain Adaptation via Compressive Attention Matching
[article]
2023
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2023; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2023 pre-print arXiv:2304.11862v2 fatcat:hogqyzmyanfgjeonrwhkdb3syyOther Versions
Universal domain adaptation (UniDA) aims to transfer knowledge from the source domain to the target domain without any prior knowledge about the label set. ...
To address this issue, we propose a Universal Attention Matching (UniAM) framework by exploiting the self-attention mechanism in vision transformer to capture the crucial object information. ...
Related Works
Universal Domain Adaptation UniDA [52] does not require prior knowledge of label set relationship. ...
arXiv:2304.11862v4
fatcat:2agntf2y6fb67lp23uhh6mynnq
Divergence Optimization for Noisy Universal Domain Adaptation
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Universal domain adaptation (UniDA) has been proposed to transfer knowledge learned from a label-rich source domain to a label-scarce target domain without any constraints on the label sets. ...
In an extensive evaluation of different domain adaptation settings, the proposed method outperformed existing methods by a large margin in most settings. ...
(ETN) [44] , (4) open-set domain adaptation method: separate to adapt (STA) [17] , and (5) universal domain adaptation methods: universal adaptation network (UAN) [41] , DANCE [24] . ...
arXiv:2104.00246v1
fatcat:5ejwatavkvgq3pafmjiwzszrcm
Subsidiary Prototype Alignment for Universal Domain Adaptation
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Universal Domain Adaptation (UniDA) deals with the problem of knowledge transfer between two datasets with domain-shift as well as category-shift. ...
To this end, we first uncover an intriguing tradeoff between negative-transfer-risk and domain-invariance exhibited at different layers of a deep network. ...
Unsupervised Domain Adaptation (DA) [13] is one of the solutions to this problem where knowledge is transferred from a labeled source domain to an unlabeled target domain. ...
arXiv:2210.15909v1
fatcat:v7q6on36vbb4dltvtui5jauzb4
OVANet: One-vs-All Network for Universal Domain Adaptation
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Universal Domain Adaptation (UNDA) aims to handle both domain-shift and category-shift between two datasets, where the main challenge is to transfer knowledge while rejecting unknown classes which are ...
Then, we adapt the open-set classifier to the target domain by minimizing class entropy. ...
The task of universal domain adaptation (UNDA) was proposed [40, 30] to account for the uncertainty about the category-shift. ...
arXiv:2104.03344v4
fatcat:n7yaj2rbxbcntjri7xfspqbuvm
Memory-Assisted Sub-Prototype Mining for Universal Domain Adaptation
[article]
2024
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2024; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Universal domain adaptation aims to align the classes and reduce the feature gap between the same category of the source and target domains. ...
The target private category is set as the unknown class during the adaptation process, as it is not included in the source domain. ...
partial domain adaptation (PDA), and universal domain adaptation (UniDA). ...
arXiv:2310.05453v3
fatcat:la4o26cjprejji4gem7goqbe44
Exploiting Inter-Sample Affinity for Knowability-Aware Universal Domain Adaptation
[article]
2023
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2023; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2023 pre-print arXiv:2207.09280v4 fatcat:vz2r56e7brczxhmmejo4newfp4Other Versions
Universal domain adaptation (UniDA) aims to transfer the knowledge of common classes from the source domain to the target domain without any prior knowledge on the label set, which requires distinguishing ...
in the target domain the unknown samples from the known ones. ...
[1] employed self-supervised learning technique to achieve the known/unknown separation and domain alignment.
Universal Domain Adaptation UDA, first introduced by You et al. ...
arXiv:2207.09280v5
fatcat:xwrpvaqgp5erlkzbfi226afvxy
« Previous
Showing results 1 — 15 out of 1,215,538 results